Related papers: MOCA: A Transformer-based Modular Causal Inference…

Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…

World models have been developed to support sample-efficient deep reinforcement learning agents. However, it remains challenging for world models to accurately replicate environments that are high-dimensional, non-stationary, and composed…

Multivariate forecasting with Transformers faces a core scalability challenge: modeling cross-channel dependencies via attention compounds attention's quadratic sequence complexity with quadratic channel scaling, making full cross-channel…

Although Transformers excel in natural language processing, their extension to time series forecasting remains challenging due to insufficient consideration of the differences between textual and temporal modalities. In this paper, we…

Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To…

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for…

Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets. Different classes of self-supervised learning offer representations with either good contextual…

Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit suboptimal accuracy in certain scenarios. By analyzing…

We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images.…

Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observing expert demonstrations. However, existing approaches typically assume homogeneous…

Multi-modal learning has shown exceptional performance in various tasks, especially in medical applications, where it integrates diverse medical information for comprehensive diagnostic evidence. However, there still are several challenges…

Multimodal sentiment analysis (MSA) aims to understand human emotions by integrating information from multiple modalities, such as text, audio, and visual data. However, existing methods often suffer from spurious correlations both within…

Unobserved confounding is one of the main challenges when estimating causal effects. We propose a causal reduction method that, given a causal model, replaces an arbitrary number of possibly high-dimensional latent confounders with a single…

Unobserved confounding is a fundamental challenge for estimating causal effects. To address unobserved confounding, recent literature has turned to two different approaches -- proxy variables and the use of multiple treatments. The first…

Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either…

This paper presents an operator-theoretic framework Linear Operator Causality Analysis (LOCA), for analysing causality in linearised dynamical systems, focusing here on fluid flows. We demonstrate that the matrix exponential of the…

Convolutional blocks have played a crucial role in advancing medical image segmentation by excelling in dense prediction tasks. However, their inability to effectively capture long-range dependencies has limited their performance.…

Attention-based models are appealing for multimodal processing because inputs from multiple modalities can be concatenated and fed to a single backbone network - thus requiring very little fusion engineering. The resulting representations…

Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data. We propose a…

Accurate estimation of treatment effects is essential for decision-making across various scientific fields. This task, however, becomes challenging in areas like social sciences and online marketplaces, where treating one experimental unit…